Automatic building extraction from satellite images, an open research topic in remote sensing, continues to represent a challenge and has received substantial attention for decades. This paper presents an object-based and machine learning-based approach for automatic house detection from RGB high-resolution images. The images are first segmented by an algorithm combing a thresholding watershed transformation and hierarchical merging, and then shadows and vegetation are eliminated from the initial segmented regions to generate building candidates. Subsequently, the candidate regions are subjected to feature extraction to generate training data. In order to capture the characteristics of house regions well, we propose two kinds of new features, namely edge regularity indices (ERI) and shadow line indices (SLI). Finally, three classifiers, namely AdaBoost, random forests, and Support Vector Machine (SVM), are employed to identify houses from test images and quality assessments are conducted. The experiments show that our method is effective and applicable for house identification. The proposed ERI and SLI features can improve the precision and recall by 5.6% and 11.2%, respectively.
With the recent development of earth observation technology, the satellites have obtained the ability to capture city-scale videos, which enable potential applications in intelligent traffic management. Because of the broad field-of-view, the moving vehicles in satellite videos are usually composed of only tens of pixels, making it difficult to differentiate true objects from noise and other distractors. In addition, the edges of tall building tops are often mistakenly detected as moving vehicles because of the effects of motion parallax. This paper proposed a terse framework that can effectively suppress false targets, achieving high precision and recall. The study involves three parts: 1) An adaptive filtering method is proposed to reduce noise, thus making the detection algorithm more reliable; 2) Several background subtraction models are tested, and the best one is chosen to produce the preliminary detection results at high recall but low accuracy; 3) A lightweight convolutional neural network (LCNN) is designed and trained on a small collection of samples, and then used to eliminate false targets. The experiments and evaluations demonstrate that our method can largely improve the precision at the expense of a slight reduction of recall.
Satellite-based video enables potential vehicle monitoring and tracking for urban traffic management. However, due to the tiny size of moving vehicles and cluttered background, it is difficult to distinguish actual targets from random noise and pseudo-moving objects, resulting in low detection accuracy. In contrast to the currently overused deep-learning-based methods, this study takes full advantage of the geometric properties of vehicle tracklets (segments of moving object trajectory) and proposes a tracklet-feature-based method that can achieve high precision and high recall. The approach is a two-step strategy: (1) smoothing filtering is used to suppress noise, and then a non-parametric-based background subtracting model is applied for obtaining preliminary recognition results with high recall but low precision; and (2) generated tracklets are used to discriminate between true and false vehicles by tracklet feature classification. Experiments and evaluations were performed on SkySat and ChangGuang acquired videos, showing that our method can improve precision and retain high recall, outperforming some classical and deep-learning methods from previously published literature.
MODIS time series data have been widely used in the research of regional and global ecosystems and climate change. For vegetation monitoring, vegetation indices such as NDVI (normalized difference vegetation index), EVI (enhanced vegetation index) and NBR (normalized burn ratio), are usually derived from MODIS reflectance data. However, noise usually makes it difficult to generate reliable time series of vegetation indices. Although some methods have been developed for reconstructing NDVI time series data, they still suffer from some limitations. First, there is no reliable approach for detecting and dealing with low-quality data, resulting in poor outcomes. Second, no effective evaluation of the fidelity of the corrected data to the original data has been discussed. For these reasons, we developed a new time series reconstruction approach, named Fixing Invalid Value (FIV) method. The proposed method assumes that the noise in surface reflectance data stems from invalid data, such as clouds, ice, and missing values. The FIV method first uses the spatially and temporally neighboring pixels to estimate the invalid values and then applies morphology operations to remove the residual noise. Finally, the Savitzky-Golay (S-G) filter is employed to generate the final results. The FIV method is tested on 8-day composite MODIS surface reflectance time series data from 2001 to 2012 in Jiangxi and Fujian provinces, China. The results show that the FIV method outperforms the conventional S-G filter and the HANTS method both in terms of visual inspection and quantitative evaluation. Furthermore, the fidelity evaluation reveals that the proposed FIV method produces high-quality time series data under all weather conditions.
Spherical harmonic (SH) has shown excellent advantages in terms of accuracy and efficiency in the retrieval of complete three-dimensional shapes. However, since the spherical function directly takes the shape centroid as the global reference point, the SH features depend heavily on the central position. In this context, the features become no longer reliable in the query of incomplete shapes that may cause erratic centroid. In this work, we propose a novel shape descriptor, namely spherical harmonic energy over the Gaussian sphere (SHE-GS), especially for the incomplete shape retrieval. Firstly, all unit normal vectors on the shape surface are mapped to points on a Gaussian sphere, which has the constant center. Secondly, kernel density estimation is used to establish a Gaussian Sphere Model (GSM) to describe the density change of these mapping points. Finally, the shape descriptor is generated by applying an SH transformation on the model. According to the way of GSM being regarded as a surface model or a volume model, we have separately designed two specific algorithm implementations. Experimental results, on two engineering shape sets containing artificially defective shapes, indicate that the proposed method outperforms other traditional methods also defined in the sphere space for incomplete shape retrieval. The superiority is verified for both similar objects in the same category or the single specific object of query.